An Explainable Counterfeit and Genuine Ethiopian Banknote Classification

Abstract

Counterfeiting is a serious crime with significant impact around the world and in Ethiopia in particular. The National Bank of Ethiopia has implemented various countermeasures to combat counterfeiting. The most successful counterfeit banknote detectors in use today are cash counters, which are hardware-based systems that use optical and magnetic sensors to detect and confirm banknotes. This technology entails an excessive cost and low availability for the public and small businesses, where the largest cash circulation occurs outside of banks. Existing countermeasures are insufficient to address this critical issue. Advancements in technology, such as digital printing and sophisticated scanning equipment, have made it easier for counterfeiters to mislead their victims by producing banknotes nearly identical to genuine ones. Only a handful of studies have been conducted on the current Ethiopian banknotes. This study presents an explainable deep learning-based model for the classification of genuine and counterfeit Ethiopian banknotes. The study used transfer learning with SHAP (Shapley Additive Explanations) and TF-EXPLAIN (TensorFlow Explain) explainable artificial intelligence frameworks for a better understanding of the classification prediction behind the models. Experimental results show that Dense121 achieved the best accuracy of 99.87%, and InceptionV3 achieved a remarkably similar result of 99.50%. To demonstrate the practical application of the model, a mobile application prototype was developed using Flutter and TensorFlow Lite. The application allows users to capture or upload images of banknotes for real-time classification without requiring internet connectivity. This solution provides an accessible and cost-effective counterfeit detection tool for the general public and small businesses.

Keywords

• Explainable AI
• Counterfeit
• Genuine
• Banknotes
• Classification
• Deep Learning

References

1. About: Counterfeit money. (n.d.). Retrieved April 3, 2023, from https://dbpedia.org/page/Counterfeit_money
2. Shefraw, A. A. (2019). Designing Ethiopian banknote classification and counterfeit verification system: an optimal feature extraction and classification techniques. Bahir Dar University Bahir Dar Institute Of Technology School Of Research And Graduate Studies (Master Thesis) http://ir.bdu.edu.et/handle/123456789/10873
3. Ali, T., Jan, S., Alkhodre, A., Nauman, M., Amin, M., & Siddiqui, M. S. (2019). DeepMoney: Counterfeit money detection using generative adversarial networks. PeerJ Computer Science, 2019(9). https://doi.org/10.7717/peerj-cs.216
4. Aseffa, D. T., Kalla, H., & Mishra, S. (2022). Ethiopian Banknote Recognition Using Convolutional Neural Network and Its Prototype Development Using Embedded Platform. Journal of Sensors, 2022. https://doi.org/10.1155/2022/4505089
5. Ayalew Tessfaw, E., Ramani, B., & Kebede Bahiru, T. (2018). Ethiopian Banknote Recognition and Fake Detection Using Support Vector Machine. 2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT), 1354–1359. https://doi.org/10.1109/ICICCT.2018.8473013
6. Counterfeit British Pound Notes from the Second World War | National Museum of American History. (n.d.). Retrieved April 27, 2023, from https://americanhistory.si.edu/the-value-of-money/new-acquisitions-building-national-numismatic-collection/counterfeit-british-pound-notes
7. Fentahun Zeggeye, J., & Assabie, Y. (2016). Automatic Recognition and Counterfeit Detection of Ethiopian Paper Currency. International Journal of Image, Graphics and Signal Processing, 8(2), 28–36. https://doi.org/10.5815/ijigsp.2016.02.04
8. Gebremeskel, G., Tadele, T. A., Girmaw, D. W., & Salau, A. O. (2022). Developing a Model for Detection of Ethiopian Fake Banknote Using Deep Learning. https://doi.org/10.21203/rs.3.rs-2282764/v1

9. Laavanya, M. & Vijayaraghavan, V.. (2019). Real Time Fake Currency Note Detection using Deep Learning. International Journal of Engineering and Advanced Technology, 9(1S5), 95–98. https://doi.org/10.35940/ijeat.a1007.1291s52019
10. Naresh Kumar, S., Singal, G., Sirikonda, S., & Nethravathi, R. (2020). A Novel Approach for Detection of Counterfeit Indian Currency Notes Using Deep Convolutional Neural Network. IOP Conference Series: Materials Science and Engineering, 981(2). https://doi.org/10.1088/1757-899X/981/2/022018
11. Padmaja, B., Shyam, P. B. N., Sagar, H. G., Nayak, B. D., & Rao, Mb. (2021). Indian Currency Denomination Recognition and Fake Currency Identification. Journal of Physics: Conference Series, 2089(1). https://doi.org/10.1088/1742-6596/2089/1/012008
12. Rahmad, C., Rohadi, E., & Lusiana, R. A. (2021). Authenticity of money using the method KNN (K-Nearest Neighbor) and CNN (Convolutional Neural Network). IOP Conference Series: Materials Science and Engineering, 1073(1), 012029. https://doi.org/10.1088/1757-899x/1073/1/012029
13. Teymournezhad, K., Azgomi, H., & Asghari, A. (2022). Detection of counterfeit banknotes by security components based on image processing and GoogLeNet deep learning network. Signal, Image and Video Processing, 16(6), 1505–1513. https://doi.org/10.1007/s11760-021-02104-z
14. The Government of Ethiopia Has Introduced New Currency Notes. - National Bank. (n.d.). Retrieved April 3, 2023, from https://nbe.gov.et/the-government-of-ethiopia-today-has-introduced-new-currency-notes/
15. The terrible effects of fake money. (n.d.). Retrieved March 14, 2023, from https://moneycounters.co.za/fake-money/
16. Yildiz, A., Ali Abd, A., Šejla, D., Nooritawati, M. T., Sherzod, T., & Mohammed, A. S. (2020). Banknotes Counterfeit Detection Using Deep Transfer Learning Approach. International Journal of Advanced Trends in Computer Science and Engineering, 9(5), 8115–8122. https://doi.org/10.30534/ijatcse/2020/172952020